{"schemaVersion":1,"target":{"type":"reading","id":"df9ac892e53ae231621ac4e805ff78da07a5f620052385bbff06acf3f1fc0777","revision":"36613ae2-b176-4c2c-8aef-996ac2c174c0","revisionKind":"publication-id","title":"arXiv cs.AI: CapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security Artifacts","url":"https://escapemeridian.com/readings/arxiv-cs-ai-caplite-prompt-injection-defense-for-small-language-df9ac892"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.17115","revision":"01c5c72409b200ebdc6a2ef67ba4371279dc39e1c9793a331c17fc69abd5c36e","revisionKind":"sha256-source-text","title":"CapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security Artifacts","url":"https://arxiv.org/abs/2611.17115"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."}